{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T16:47:25Z","timestamp":1770742045797,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the Science and Technology Major Project of Commission of Science and Technology of Shanghai","award":["2021SHZDZX0103"],"award-info":[{"award-number":["2021SHZDZX0103"]}]},{"name":"National Natural Science Foundation of China","award":["61976057"],"award-info":[{"award-number":["61976057"]}]},{"name":"the Science and Technology Commission of Shanghai Municipality","award":["20511100800"],"award-info":[{"award-number":["20511100800"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1145\/3474085.3475677","type":"proceedings-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T04:59:18Z","timestamp":1634533158000},"page":"5047-5055","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Exploring Logical Reasoning for Referring Expression Comprehension"],"prefix":"10.1145","author":[{"given":"Ying","family":"Cheng","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruize","family":"Wang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiashuo","family":"Yu","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui-Wei","family":"Zhao","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuejie","family":"Zhang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Feng","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_1_3_1","volume-title":"Logic-Guided Data Augmentation and Regularization for Consistent Question Answering. arXiv preprint arXiv:2004.10157","author":"Asai Akari","year":"2020"},{"key":"e_1_3_2_1_4_1","volume-title":"Faisal Ahmed, Zhe Gan, Yu Cheng, and Jingjing Liu.","author":"Chen Yen-Chun","year":"2020"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"32","author":"Cirik Volkan","year":"2018"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Thomas Demeester Tim Rockt\u00e4schel and Sebastian Riedel. 2016. Lifted rule injection for relation embeddings. In EMNLP. 1389--1399.  Thomas Demeester Tim Rockt\u00e4schel and Sebastian Riedel. 2016. Lifted rule injection for relation embeddings. In EMNLP. 1389--1399.","DOI":"10.18653\/v1\/D16-1146"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00808"},{"key":"e_1_3_2_1_8_1","unstructured":"Honghua Dong Jiayuan Mao Tian Lin Chong Wang Lihong Li and Denny Zhou. 2019. Neural logic machines. In ICLR.  Honghua Dong Jiayuan Mao Tian Lin Chong Wang Lihong Li and Denny Zhou. 2019. Neural logic machines. In ICLR."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/3241691.3241692"},{"key":"e_1_3_2_1_10_1","unstructured":"Marc Fischer Mislav Balunovic Dana Drachsler-Cohen Timon Gehr Ce Zhang and Martin Vechev. 2019. Dl2: Training and querying neural networks with logic. In ICML. 1931--1941.  Marc Fischer Mislav Balunovic Dana Drachsler-Cohen Timon Gehr Ce Zhang and Martin Vechev. 2019. Dl2: Training and querying neural networks with logic. In ICML. 1931--1941."},{"key":"e_1_3_2_1_11_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. 770--778.  Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. 770--778."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_13_1","volume-title":"A Recurrent Vision-and-Language BERT for Navigation. arXiv preprint arXiv:2011.13922","author":"Hong Yicong","year":"2020"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.470"},{"key":"e_1_3_2_1_15_1","unstructured":"Zhiting Hu Xuezhe Ma Zhengzhong Liu Eduard Hovy and Eric Xing. 2016. Harnessing deep neural networks with logic rules. In ACL.  Zhiting Hu Xuezhe Ma Zhengzhong Liu Eduard Hovy and Eric Xing. 2016. Harnessing deep neural networks with logic rules. In ACL."},{"key":"e_1_3_2_1_16_1","volume-title":"ask, attend, and answer: A strong baseline for visual question answering. arXiv preprint arXiv:1704.03162","author":"Kazemi Vahid","year":"2017"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 6741--6749","author":"Ke Liyiming","year":"2019"},{"key":"e_1_3_2_1_19_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00145"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Tao Li Vivek Gupta Maitrey Mehta and Vivek Srikumar. 2019. A Logic-Driven Framework for Consistency of Neural Models. In EMNLP-IJCNLP. 3922--3933.  Tao Li Vivek Gupta Maitrey Mehta and Vivek Srikumar. 2019. A Logic-Driven Framework for Consistency of Neural Models. In EMNLP-IJCNLP. 3922--3933.","DOI":"10.18653\/v1\/D19-1405"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Tao Li and Vivek Srikumar. 2019. Augmenting neural networks with first-order logic. In ACL. 292--302.  Tao Li and Vivek Srikumar. 2019. Augmenting neural networks with first-order logic. In ACL. 292--302.","DOI":"10.18653\/v1\/P19-1028"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00205"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6833"},{"key":"e_1_3_2_1_29_1","volume-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. arXiv preprint arXiv:1908.02265","author":"Lu Jiasen","year":"2019"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.333"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_1_33_1","volume-title":"Referring Expression Comprehension: A Survey of Methods and Datasets","author":"Qiao Yanyuan","year":"2020"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969239.2969250"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295136"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1118"},{"key":"e_1_3_2_1_37_1","volume-title":"Vl-bert: Pre-training of generic visual-linguistic representations. arXiv preprint arXiv:1908.08530","author":"Su Weijie","year":"2019"},{"key":"e_1_3_2_1_38_1","volume-title":"Deep probabilistic logic: A unifying framework for indirect supervision. arXiv preprint arXiv:1808.08485","author":"Wang Hai","year":"2018"},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 1960--1968","author":"Wang Peng"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"e_1_3_2_1_41_1","unstructured":"Jingyi Xu Zilu Zhang Tal Friedman Yitao Liang and Guy Van den Broeck. 2018. A semantic loss function for deep learning with symbolic knowledge. In ICML. 5498--5507.  Jingyi Xu Zilu Zhang Tal Friedman Yitao Liang and Guy Van den Broeck. 2018. A semantic loss function for deep learning with symbolic knowledge. In ICML. 5498--5507."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.5555\/3294771.3294992"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00427"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00474"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.375"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00437"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00447"}],"event":{"name":"MM '21: ACM Multimedia Conference","location":"Virtual Event China","acronym":"MM '21","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 29th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475677","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3475677","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:25Z","timestamp":1750193305000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475677"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":50,"alternative-id":["10.1145\/3474085.3475677","10.1145\/3474085"],"URL":"https:\/\/doi.org\/10.1145\/3474085.3475677","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]},"assertion":[{"value":"2021-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}